Search

A typical back-propagation neural network (BPN) model is developed for modelling radio propagation for field strength prediction based on data measurements of propagation loss (in decibels) with terrain information taken in an urban area (Athens region) in the 900 MHz band. The feasibility of the BPN model is checked against the performance of a conventional semiempirical reference model. The performance of both models is quantified by statistical methods. The evaluation is done by comparing their prediction error statistics of average absolute, standard deviation and root mean square and by comparing their percentage accuracy and correlation of predicted values relative to true data measurements. © 1998 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

To understand the propagation structure of the microcells with a tall and medium-height antenna in an urban area, the fundamental propagation parameters are found and the structural model of the propagation loss was constructed. The fundamental propagation parameters were obtained based on the multivariable analysis of the propagation data at 800 MHz measured m the Tokyo Metropolitan area. These parameters are the distance between the transmitter and receiver, the average building height between the transmitter and receiver, and the base-station height which have high correlation and regression coefficients with the propagation loss. The relationship of parameters obtained from the model is (20 - α) log(h) for the base-station height characteristics and (α - 20) log (H) for the building height characteristics if the distance characteristics are α log (d). The relationships of coefficients of the conventional estimation equation and the regression equation obtained by the measured data almost agreed with those of the model so that the validity of the model was confirmed. [ABSTRACT FROM AUTHOR]